Creation of Language Resources for the Development of a Medical Speech Recognition System for Latvian

Abstract

This paper describes an ongoing work on the creation of Latvian language resources for the medical domain focusing on digital imaging to develop a medical speech recognition system for Latvian. The language resources include a pronunciation lexicon, a text corpus for language modelling, and an orthographically transcribed speech corpus for the (i) adaptation of the acoustic model, (ii) evaluation of the speech recognition accuracy, (iii) development and testing of rewrite rules for automatic text conversion to the spoken form and back to the written form. This work is part of a larger industry-driven research project which aims at the development of specific Latvian speech recognition systems for the medical domain.

RUTA:MED – Dual Workflow Medical Speech Transcription Pipeline and Editor

“…RUTA:MED builds on our previous work on a general-domain speech transcription system for Latvian [5], which we have adapted and extended for the medical domain [1,2]. The platform is showcased with the less resourced Latvian language and the situation in Latvia regarding the usage of automatic speech recognition (ASR) and text processing technologies in the medical domain, however, the Latvian case is not unique.…”

“…The Latvian-specific resources and components of RUTA:MED are described in more detail by Dargis et al [1] and Gruzitis et al [2]. In this system demo paper, we focus on the whole platform and the dual workflow it supports.…”